openviking-context-database

Use OpenViking from OpenClaw through @openviking/openclaw-plugin: long-term memory, session archives, resource and Agent Skill import, semantic recall, recall trace debugging, and externalized tool-result recovery. Prefer this skill when the user wants to use, query, debug, or operate OpenViking context from an OpenClaw agent. For first-time plugin installation, use the install-openviking-memory skill instead.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, dense operator reference with concrete commands, complete tool parameter tables, and a strong troubleshooting table. Its main weaknesses are token weight from inlining the full config and tool reference in SKILL.md, and the absence of any bundle-level progressive disclosure — the referenced repo docs are not present in the skill bundle.

Suggestions

Move the full 'Configuration Quick Reference' table and per-tool parameter tables into references/ files (e.g. references/config.md, references/tools.md), keeping only the status/setup commands and the tool selection guide in SKILL.md.

Add a short end-to-end operational workflow section (check status → setup → verify health/slot → select tool) with explicit validation checkpoints, rather than relying on section order to imply the sequence.

Either include the referenced docs (README.md, INSTALL.md, docs/openviking-openclaw-plugin-guide.md) in the skill bundle as references/ files or replace that section with pointers to files that actually ship with the skill.

Dimension	Reasoning	Score
Conciseness	Dense tables and imperative notes with no padding or explanation of concepts Claude already knows. Not 5 because the always-loaded body carries a 30-row config table and a full per-tool parameter reference that add notable token weight; not 3 because it is mostly efficient with only minor trimming opportunities.	4 / 5
Actionability	Copy-paste-ready commands ("openclaw openviking status --json", five concrete setup variants), per-tool parameter tables with defaults, slash-command examples, and a symptom→cause→first-action troubleshooting table. Fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	Sequencing is present ("Read status first" before setup), with explicit checkpoints such as "do not delete ambiguous memories; ask the user to choose the exact URI" and "Try at least two concrete keyword variants before concluding". Not 5 because the overall shape is a reference guide — the end-to-end operational flow is implied by section order rather than presented as an explicit validated sequence.	4 / 5
Progressive Disclosure	Sections are well-organized and clearly headed, but the entire configuration reference and tool API reference are inlined in SKILL.md instead of being split into bundle files, and the "Reference Docs in This Repo" section points to files that are not part of the skill bundle (no references/ directory exists). This matches the 3 anchor ('content that should be separate is inline'), not 4, because the bulk detail material is not split out.	3 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete capability enumeration, an explicit 'prefer this skill when...' trigger clause, and active disambiguation from the related install skill. Voice is third person ("when the user wants to") with no first/second-person constructions. The only weakness is slightly limited synonym coverage of natural trigger phrases.

Dimension	Reasoning	Score
Specificity	The description enumerates six concrete, distinct capabilities ("long-term memory, session archives, resource and Agent Skill import, semantic recall, recall trace debugging, and externalized tool-result recovery"), comprehensively covering the plugin's feature surface. It fits the 5 anchor rather than 4 because coverage shows no notable gaps.	5 / 5
Completeness	It explicitly answers what (the six-capability list tied to "@openviking/openclaw-plugin") and when ("Prefer this skill when the user wants to use, query, debug, or operate OpenViking context from an OpenClaw agent"), with concrete trigger phrases and an added boundary clause for installation.	5 / 5
Trigger Term Quality	Good keyword coverage with natural phrases users would say ("long-term memory", "session archives", "use, query, debug, or operate") plus the product names themselves. Not 5 because a few natural synonyms are missing (e.g. "remember this", "search my past chats"); not 3 because coverage is broad, not partial.	4 / 5
Distinctiveness Conflict Risk	A clear niche anchored to a named plugin, with an explicit disambiguation redirect ("For first-time plugin installation, use the install-openviking-memory skill instead") that minimizes overlap risk with the sibling install skill.	5 / 5
	Total	19 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: volcengine/OpenViking
Path: examples/openclaw-plugin/skills/openviking-context-database/SKILL.md
Commit: b2f1f9d

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.